EDA LA2

Name: — USN:

Akhilesh Kumar Mishra — 1nt19is010

Prarabdh Joshi — 1nt19is114

The dataset has three attributes Age , Estimated Salary , Purchased. Target value is purchased which is based on the Attributes Age and EStimated salary .

based on the analysis of the graphs conclusion::

if the persons is age is above 40years and the salary is above 80k then the purchase is high i.e 1. (Exceptions are also present).


getwd()
## [1] "D:/sna"
setwd("D:/sna")
getwd()
## [1] "D:/sna"
  df<-read.csv("D:\\sna\\Social_Network_Ads.csv")
df
##     Age EstimatedSalary Purchased
## 1    19           19000         0
## 2    35           20000         0
## 3    26           43000         0
## 4    27           57000         0
## 5    19           76000         0
## 6    27           58000         0
## 7    27           84000         0
## 8    32          150000         1
## 9    25           33000         0
## 10   35           65000         0
## 11   26           80000         0
## 12   26           52000         0
## 13   20           86000         0
## 14   32           18000         0
## 15   18           82000         0
## 16   29           80000         0
## 17   47           25000         1
## 18   45           26000         1
## 19   46           28000         1
## 20   48           29000         1
## 21   45           22000         1
## 22   47           49000         1
## 23   48           41000         1
## 24   45           22000         1
## 25   46           23000         1
## 26   47           20000         1
## 27   49           28000         1
## 28   47           30000         1
## 29   29           43000         0
## 30   31           18000         0
## 31   31           74000         0
## 32   27          137000         1
## 33   21           16000         0
## 34   28           44000         0
## 35   27           90000         0
## 36   35           27000         0
## 37   33           28000         0
## 38   30           49000         0
## 39   26           72000         0
## 40   27           31000         0
## 41   27           17000         0
## 42   33           51000         0
## 43   35          108000         0
## 44   30           15000         0
## 45   28           84000         0
## 46   23           20000         0
## 47   25           79000         0
## 48   27           54000         0
## 49   30          135000         1
## 50   31           89000         0
## 51   24           32000         0
## 52   18           44000         0
## 53   29           83000         0
## 54   35           23000         0
## 55   27           58000         0
## 56   24           55000         0
## 57   23           48000         0
## 58   28           79000         0
## 59   22           18000         0
## 60   32          117000         0
## 61   27           20000         0
## 62   25           87000         0
## 63   23           66000         0
## 64   32          120000         1
## 65   59           83000         0
## 66   24           58000         0
## 67   24           19000         0
## 68   23           82000         0
## 69   22           63000         0
## 70   31           68000         0
## 71   25           80000         0
## 72   24           27000         0
## 73   20           23000         0
## 74   33          113000         0
## 75   32           18000         0
## 76   34          112000         1
## 77   18           52000         0
## 78   22           27000         0
## 79   28           87000         0
## 80   26           17000         0
## 81   30           80000         0
## 82   39           42000         0
## 83   20           49000         0
## 84   35           88000         0
## 85   30           62000         0
## 86   31          118000         1
## 87   24           55000         0
## 88   28           85000         0
## 89   26           81000         0
## 90   35           50000         0
## 91   22           81000         0
## 92   30          116000         0
## 93   26           15000         0
## 94   29           28000         0
## 95   29           83000         0
## 96   35           44000         0
## 97   35           25000         0
## 98   28          123000         1
## 99   35           73000         0
## 100  28           37000         0
## 101  27           88000         0
## 102  28           59000         0
## 103  32           86000         0
## 104  33          149000         1
## 105  19           21000         0
## 106  21           72000         0
## 107  26           35000         0
## 108  27           89000         0
## 109  26           86000         0
## 110  38           80000         0
## 111  39           71000         0
## 112  37           71000         0
## 113  38           61000         0
## 114  37           55000         0
## 115  42           80000         0
## 116  40           57000         0
## 117  35           75000         0
## 118  36           52000         0
## 119  40           59000         0
## 120  41           59000         0
## 121  36           75000         0
## 122  37           72000         0
## 123  40           75000         0
## 124  35           53000         0
## 125  41           51000         0
## 126  39           61000         0
## 127  42           65000         0
## 128  26           32000         0
## 129  30           17000         0
## 130  26           84000         0
## 131  31           58000         0
## 132  33           31000         0
## 133  30           87000         0
## 134  21           68000         0
## 135  28           55000         0
## 136  23           63000         0
## 137  20           82000         0
## 138  30          107000         1
## 139  28           59000         0
## 140  19           25000         0
## 141  19           85000         0
## 142  18           68000         0
## 143  35           59000         0
## 144  30           89000         0
## 145  34           25000         0
## 146  24           89000         0
## 147  27           96000         1
## 148  41           30000         0
## 149  29           61000         0
## 150  20           74000         0
## 151  26           15000         0
## 152  41           45000         0
## 153  31           76000         0
## 154  36           50000         0
## 155  40           47000         0
## 156  31           15000         0
## 157  46           59000         0
## 158  29           75000         0
## 159  26           30000         0
## 160  32          135000         1
## 161  32          100000         1
## 162  25           90000         0
## 163  37           33000         0
## 164  35           38000         0
## 165  33           69000         0
## 166  18           86000         0
## 167  22           55000         0
## 168  35           71000         0
## 169  29          148000         1
## 170  29           47000         0
## 171  21           88000         0
## 172  34          115000         0
## 173  26          118000         0
## 174  34           43000         0
## 175  34           72000         0
## 176  23           28000         0
## 177  35           47000         0
## 178  25           22000         0
## 179  24           23000         0
## 180  31           34000         0
## 181  26           16000         0
## 182  31           71000         0
## 183  32          117000         1
## 184  33           43000         0
## 185  33           60000         0
## 186  31           66000         0
## 187  20           82000         0
## 188  33           41000         0
## 189  35           72000         0
## 190  28           32000         0
## 191  24           84000         0
## 192  19           26000         0
## 193  29           43000         0
## 194  19           70000         0
## 195  28           89000         0
## 196  34           43000         0
## 197  30           79000         0
## 198  20           36000         0
## 199  26           80000         0
## 200  35           22000         0
## 201  35           39000         0
## 202  49           74000         0
## 203  39          134000         1
## 204  41           71000         0
## 205  58          101000         1
## 206  47           47000         0
## 207  55          130000         1
## 208  52          114000         0
## 209  40          142000         1
## 210  46           22000         0
## 211  48           96000         1
## 212  52          150000         1
## 213  59           42000         0
## 214  35           58000         0
## 215  47           43000         0
## 216  60          108000         1
## 217  49           65000         0
## 218  40           78000         0
## 219  46           96000         0
## 220  59          143000         1
## 221  41           80000         0
## 222  35           91000         1
## 223  37          144000         1
## 224  60          102000         1
## 225  35           60000         0
## 226  37           53000         0
## 227  36          126000         1
## 228  56          133000         1
## 229  40           72000         0
## 230  42           80000         1
## 231  35          147000         1
## 232  39           42000         0
## 233  40          107000         1
## 234  49           86000         1
## 235  38          112000         0
## 236  46           79000         1
## 237  40           57000         0
## 238  37           80000         0
## 239  46           82000         0
## 240  53          143000         1
## 241  42          149000         1
## 242  38           59000         0
## 243  50           88000         1
## 244  56          104000         1
## 245  41           72000         0
## 246  51          146000         1
## 247  35           50000         0
## 248  57          122000         1
## 249  41           52000         0
## 250  35           97000         1
## 251  44           39000         0
## 252  37           52000         0
## 253  48          134000         1
## 254  37          146000         1
## 255  50           44000         0
## 256  52           90000         1
## 257  41           72000         0
## 258  40           57000         0
## 259  58           95000         1
## 260  45          131000         1
## 261  35           77000         0
## 262  36          144000         1
## 263  55          125000         1
## 264  35           72000         0
## 265  48           90000         1
## 266  42          108000         1
## 267  40           75000         0
## 268  37           74000         0
## 269  47          144000         1
## 270  40           61000         0
## 271  43          133000         0
## 272  59           76000         1
## 273  60           42000         1
## 274  39          106000         1
## 275  57           26000         1
## 276  57           74000         1
## 277  38           71000         0
## 278  49           88000         1
## 279  52           38000         1
## 280  50           36000         1
## 281  59           88000         1
## 282  35           61000         0
## 283  37           70000         1
## 284  52           21000         1
## 285  48          141000         0
## 286  37           93000         1
## 287  37           62000         0
## 288  48          138000         1
## 289  41           79000         0
## 290  37           78000         1
## 291  39          134000         1
## 292  49           89000         1
## 293  55           39000         1
## 294  37           77000         0
## 295  35           57000         0
## 296  36           63000         0
## 297  42           73000         1
## 298  43          112000         1
## 299  45           79000         0
## 300  46          117000         1
## 301  58           38000         1
## 302  48           74000         1
## 303  37          137000         1
## 304  37           79000         1
## 305  40           60000         0
## 306  42           54000         0
## 307  51          134000         0
## 308  47          113000         1
## 309  36          125000         1
## 310  38           50000         0
## 311  42           70000         0
## 312  39           96000         1
## 313  38           50000         0
## 314  49          141000         1
## 315  39           79000         0
## 316  39           75000         1
## 317  54          104000         1
## 318  35           55000         0
## 319  45           32000         1
## 320  36           60000         0
## 321  52          138000         1
## 322  53           82000         1
## 323  41           52000         0
## 324  48           30000         1
## 325  48          131000         1
## 326  41           60000         0
## 327  41           72000         0
## 328  42           75000         0
## 329  36          118000         1
## 330  47          107000         1
## 331  38           51000         0
## 332  48          119000         1
## 333  42           65000         0
## 334  40           65000         0
## 335  57           60000         1
## 336  36           54000         0
## 337  58          144000         1
## 338  35           79000         0
## 339  38           55000         0
## 340  39          122000         1
## 341  53          104000         1
## 342  35           75000         0
## 343  38           65000         0
## 344  47           51000         1
## 345  47          105000         1
## 346  41           63000         0
## 347  53           72000         1
## 348  54          108000         1
## 349  39           77000         0
## 350  38           61000         0
## 351  38          113000         1
## 352  37           75000         0
## 353  42           90000         1
## 354  37           57000         0
## 355  36           99000         1
## 356  60           34000         1
## 357  54           70000         1
## 358  41           72000         0
## 359  40           71000         1
## 360  42           54000         0
## 361  43          129000         1
## 362  53           34000         1
## 363  47           50000         1
## 364  42           79000         0
## 365  42          104000         1
## 366  59           29000         1
## 367  58           47000         1
## 368  46           88000         1
## 369  38           71000         0
## 370  54           26000         1
## 371  60           46000         1
## 372  60           83000         1
## 373  39           73000         0
## 374  59          130000         1
## 375  37           80000         0
## 376  46           32000         1
## 377  46           74000         0
## 378  42           53000         0
## 379  41           87000         1
## 380  58           23000         1
## 381  42           64000         0
## 382  48           33000         1
## 383  44          139000         1
## 384  49           28000         1
## 385  57           33000         1
## 386  56           60000         1
## 387  49           39000         1
## 388  39           71000         0
## 389  47           34000         1
## 390  48           35000         1
## 391  48           33000         1
## 392  47           23000         1
## 393  45           45000         1
## 394  60           42000         1
## 395  39           59000         0
## 396  46           41000         1
## 397  51           23000         1
## 398  50           20000         1
## 399  36           33000         0
## 400  49           36000         1

2.Scatter plot

  plot(df$Age, df$EstimatedSalary)

scatter plot using ggplot.

  library(ggplot2)
ggplot(df, aes(x = Age, y = EstimatedSalary )) +
 geom_point()

3.

ggplot(data = NULL, aes(x = df$Age, y = df$EstimatedSalary)) +
 geom_point()

4.creating line graph

plot(df$Age, df$EstimatedSalary, type = "l")

  1. scatter + points graph
plot(df$Age, df$EstimatedSalary, type = "l")
points(df$Age, df$EstimatedSalary)

6. estimated Salary divided by 2 and color of line changed to red

plot(df$Age, df$EstimatedSalary/2, col="red",type="l")
points(df$Age, df$EstimatedSalary, col="red")

7.using gg plot line graph

library(ggplot2)
ggplot(df, aes(x = Age, y = EstimatedSalary )) +
 geom_line()

8. ggplot scatter + line

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point()

  1. creating a bar graph
barplot(df$Age, names.arg = df$EstimatedSalary)

10.barplot of AGE

barplot(table(df$Age))

11. barplot of EStimatedSalary

  barplot(table(df$EstimatedSalary))

12.bargraph using ggplot

library(ggplot2)
# Bar graph of values. This uses the BOD data frame, with the
# "Time" column for x values and the "demand" column for y values.
ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col()

13.Convert the x variable to a factor, so that it is treated as discrete

ggplot(df, aes(x = factor(Purchased), y = EstimatedSalary)) +
 geom_col()

  1. Bar graph of counts
  ggplot(df, aes(x = Age)) +
 geom_bar()

15.Histogram

  hist(df$Age)

  1. hist of salalry
  hist(df$EstimatedSalary)

17. hist of purchased

   hist(df$Purchased)

  1. histogram with ggplot2
  library(ggplot2)
ggplot(df, aes(x = Age)) +
 geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

19.histogram with ggplot2 of Estimated salary

  library(ggplot2)
ggplot(df, aes(x = EstimatedSalary)) +
 geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

20.With wider bins

  ggplot(df, aes(x = Age)) +
 geom_histogram(binwidth = 4)

  1. creating a box plot
    boxplot(Age ~ EstimatedSalary, data = df)

22.Put interaction of two variables on x-axis

boxplot(Age ~ EstimatedSalary + Purchased, data = df)

23.boxplot using ggplot2

  library(ggplot2)
ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_boxplot()
## Warning: Continuous x aesthetic -- did you forget aes(group=...)?

  1. boxplot (x interaction)
  ggplot(df, aes(x = interaction(EstimatedSalary,Purchased ), y = Age)) +
 geom_boxplot()

25. Plotting a Function Curve

  curve(x^3 - 5*x, from = -4, to = 4)

26. Plot a user-defined function

  myfun <- function(xvar) {
 1 / (1 + exp(-xvar + 10))
}
curve(myfun(x), from = 0, to = 20)
# Add a line:
curve(1 - myfun(x), add = TRUE, col = "red")

27.using ggplot2

  library(ggplot2)
  # This sets the x range from 0 to 20
  ggplot(data.frame(x = c(0, 20)), aes(x = x)) +
  stat_function(fun = myfun, geom = "line")

chapter 3

library(gcookbook) # Load gcookbook for the pg_mean data set
ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col()

29.

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col()

ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col(fill = "lightblue", colour = "black")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(position = "dodge")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased)))+
 geom_col(position = "dodge", colour = "black") +
 scale_fill_brewer(palette = "Pastel1")

33.

  ggplot(df, aes(x = Age)) +
 geom_bar()

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col()

  ggplot(df, aes(x = reorder(Age, EstimatedSalary), y = EstimatedSalary, fill = factor(Purchased))) +
  geom_col(colour = "black") +
  scale_fill_manual(values = c("#669933", "#FFCC66")) +
  xlab("State")

ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_col(position = "identity", colour = "black", size = 0.25) +
 scale_fill_manual(values = c("#CCEEFF", "#FFDDDD"), guide = FALSE)
## Warning: It is deprecated to specify `guide = FALSE` to remove a guide. Please
## use `guide = "none"` instead.

  1. Adjusting Bar Width and Spacing
  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col()

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col(width=0.5)

    ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_col(width=1) 

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(width = 0.5, position = "dodge")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(width = 0.5, position = position_dodge(0.7))

  ggplot(df, aes(x = Age , y = EstimatedSalary, fill = Purchased)) +
 geom_col()

43.

    ggplot(df, aes(x = Age, y =EstimatedSalary , fill = Purchased)) +
 geom_col() +
 guides(fill = guide_legend(reverse = TRUE))

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(position = position_stack(reverse = TRUE)) +
 guides(fill = guide_legend(reverse = TRUE))

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_col(colour = "black") +
 scale_fill_brewer(palette = "Pastel1")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(position = "fill")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(position = "fill") +
 scale_y_continuous(labels = scales::percent)

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_col(colour = "black", position = "fill") +
 scale_y_continuous(labels = scales::percent) +
 scale_fill_brewer(palette = "Pastel1")

49.

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col()

  ggplot(df, aes(x = interaction(Age, Purchased), y = EstimatedSalary)) +
 geom_col() +
 geom_text(aes(label = EstimatedSalary), vjust = 1.5, colour = "white")

  ggplot(df, aes(x = interaction(Age, Purchased), y = EstimatedSalary)) +
  geom_col() +
  geom_text(aes(label = EstimatedSalary), vjust = -0.2)

  ggplot(df, aes(x = factor(Purchased))) +
 geom_bar() +
 geom_text(aes(label = ..count..), stat = "count", vjust = 1.5,
 colour = "white")

  ggplot(df, aes(x = interaction(Age, Purchased), y = EstimatedSalary)) +
 geom_col() +
 geom_text(aes(label = EstimatedSalary), vjust = -0.2) +
 ylim(0, max(df$EstimatedSalary) * 1.05)
## Warning: Removed 279 rows containing missing values (geom_col).

  ggplot(df, aes(x = interaction(Age, Purchased), y = EstimatedSalary)) +
 geom_col() +
 geom_text(aes(y = EstimatedSalary + 0.1, label = EstimatedSalary))

ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col(position = "dodge") +
 geom_text(
 aes(label = EstimatedSalary),
 colour = "white", size = 3,
 vjust = 1.5, position = position_dodge(.9))

56.

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
  geom_col() +
 geom_text(aes(y = EstimatedSalary, label = EstimatedSalary), vjust = 1.5, colour = "white")

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = Purchased)) +
 geom_col() +
 geom_text(aes(y = EstimatedSalary, label = EstimatedSalary), colour = "white")

  ggplot(df, aes(x =Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_col(colour = "black") +
 geom_text(aes(y = EstimatedSalary,
 label = paste(format(EstimatedSalary, nsmall = 2), "kg")),
 size = 4) +
 scale_fill_brewer(palette = "Pastel1")

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_point()

ggplot(df, aes(x = Age, y = reorder(Age, EstimatedSalary))) +
 geom_point(size = 3) + # Use a larger dot
 theme_bw() +
 theme(
 panel.grid.major.x = element_blank(),
 panel.grid.minor.x = element_blank(),
 panel.grid.major.y = element_line(colour = "grey60", linetype = "dashed")
 )

  ggplot(df, aes(x = reorder(Age, EstimatedSalary), y = EstimatedSalary)) +
 geom_point(size = 3) + # Use a larger dot
 theme_bw() +
 theme(
 panel.grid.major.y = element_blank(),
 panel.grid.minor.y = element_blank(),
 panel.grid.major.x = element_line(colour = "grey60", linetype = "dashed"),
 axis.text.x = element_text(angle = 60, hjust = 1)
 )

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_segment(aes(yend = Age), xend = 0, colour = "grey50") +
 geom_point(size = 3, aes(colour = factor(Purchased))) +
 scale_colour_brewer(palette = "Set1", limits = c("NL", "AL")) +
 theme_bw() +
 theme(
 panel.grid.major.y = element_blank(), # No horizontal grid lines
 legend.position = c(1, 0.55), # Put legend inside plot area
 legend.justification = c(1, 0.5)
 )
## Warning: Removed 400 rows containing missing values (geom_point).

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_segment(aes(yend = Age), xend = 0, colour = "grey50") +
 geom_point(size = 3, aes(colour = factor(Purchased))) +
 scale_colour_brewer(palette = "Set1", limits = c("NL", "AL"), guide = FALSE) +
 theme_bw() +
 theme(panel.grid.major.y = element_blank()) +
 facet_grid(Purchased ~ ., scales = "free_y", space = "free_y")
## Warning: Removed 400 rows containing missing values (geom_point).
## Warning: It is deprecated to specify `guide = FALSE` to remove a guide. Please
## use `guide = "none"` instead.

64.

    ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line()

  df1 <- df # Make a copy of the data
df1$Purchased <- factor(df$Purchased)
ggplot(df, aes(x = Age, y = EstimatedSalary, group = 1)) +
 geom_line()

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 ylim(0, max(df$EstimatedSalary))

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 expand_limits(y = 0)

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point()

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point()

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point() +
 scale_y_log10()

  ggplot(df, aes(x = Age, y = EstimatedSalary, colour = Purchased)) +
 geom_line()

72.

  ggplot(df, aes(x = Age, y = EstimatedSalary, linetype = factor(Purchased))) +
 geom_line()

  ggplot(df, aes(x = factor(Purchased), y = Age, colour = EstimatedSalary, group = Age)) +
 geom_line()

  ggplot(df, aes(x = factor(Purchased), y = Age, colour = Age)) + geom_line()

  ggplot(df, aes(x = Purchased, y = EstimatedSalary)) +
 geom_line()

  ggplot(df, aes(x = Age, y = EstimatedSalary, shape = factor(Purchased))) +
 geom_line() +
 geom_point(size = 4)

   ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_line() +
 geom_point(size = 4, shape = 21)   

  ggplot(df, aes(x = Age, y = EstimatedSalary, shape = factor(Purchased))) +
 geom_line(position = position_dodge(0.2)) + 
 geom_point(position = position_dodge(0.2), size = 4) 

79.

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line(linetype = "dashed", size = 1, colour = "blue")

  ggplot(df ,aes(x = Age, y = EstimatedSalary, colour = factor(Purchased))) +
 geom_line() +
 scale_colour_brewer(palette = "Set1")

81.

  ggplot(df, aes(x = Age, y = EstimatedSalary, group = Purchased)) +
 geom_line(colour = "darkgreen", size = 1.5)

  ggplot(df, aes(x = Age, y = EstimatedSalary, colour = factor(Purchased))) +
 geom_line(linetype = "dashed") +
 geom_point(shape = 22, size = 3, fill = "white")

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point(size = 4, shape = 22, colour = "darkred", fill = "pink")

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line() +
 geom_point(size = 4, shape = 21, fill = "white")

  pd <- position_dodge(0.2)
ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_line(position = pd) +
 geom_point(shape = 21, size = 3, position = pd) +
 scale_fill_manual(values = c("black","white"))

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_area()

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_area(fill = "blue", alpha = .2) +
 geom_line()

88.

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_area()

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_area(colour = "black", size = .2, alpha = .4) +
 scale_fill_brewer(palette = "Blues")

    ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased),
 order = dplyr::desc(EstimatedSalary))) +
 geom_area(colour = NA, alpha = .4) +
 scale_fill_brewer(palette = "Blues") +
 geom_line(position = "stack", size = .2)

  ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_area(position = "fill", colour = "black", size = .2, alpha = .4) +
 scale_fill_brewer(palette = "Blues")

92.

    ggplot(df, aes(x = Age, y = EstimatedSalary, fill = factor(Purchased))) +
 geom_area(position = "fill", colour = "black", size = .2, alpha = .4) +
 scale_fill_brewer(palette = "Blues") +
 scale_y_continuous(labels = scales::percent)

 ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_line(aes(y = EstimatedSalary - Purchased), colour = "grey50",
 linetype = "dotted") +
 geom_line(aes(y =EstimatedSalary + Purchased), colour = "grey50",
 linetype = "dotted") +
 geom_line()

  ggplot(df, aes(x = Age, y = EstimatedSalary, shape = factor(Purchased), colour = factor(Purchased))) +
 geom_point() +
 scale_shape_manual(values = c(1,2)) +
 scale_colour_brewer(palette = "Set1")

  ggplot(df, aes(x = Age, y = EstimatedSalary, shape = factor(Purchased))) +
 geom_point(size = 3) +
 scale_shape_manual(values = c(1, 4))

    ggplot(df, aes(x = Age, y = EstimatedSalary, shape = factor(Purchased), fill = factor(Purchased))) +
 geom_point(size = 2.5) +
 scale_shape_manual(values = c(21, 24)) +
 scale_fill_manual(
 values = c(NA, "black"),
 guide = guide_legend(override.aes = list(shape = 21))
 )

df3 <- ggplot(df, aes(x = Age, y = EstimatedSalary))
df3 +
 geom_point()

df3 +
 stat_bin2d(bins = 50) +
 scale_fill_gradient(low = "lightblue", high = "red", limits = c(0, 6000))

  ggplot(df, aes(x = Age, y = EstimatedSalary)) +
 geom_point(
 position = position_jitter(width = 0.3, height = 0.06),
 alpha = 0.4,
 shape = 21,
 size = 1.5
 ) +
 stat_smooth(method = glm, method.args = list(family = binomial))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Computation failed in `stat_smooth()`:
## y values must be 0 <= y <= 1

ggplot(df, aes(x =Age, y = EstimatedSalary)) +
 geom_point(
 position = position_jitter(width = .3, height = .08),
 alpha = 0.4,
 shape = 21,
 size = 1.5
 ) +
 geom_line(data = df, colour = "#1177FF", size = 1)

##Github Repository https://github.com/akhil-k-m/eda_la/blob/main/la2history.Rhistory